… While this work has considered blind symbol decoding, the dual path concept can be
extended to other problems in wireless communications leveraging deep learning. By using a …

… In this work, we propose a deep learning approach combined with receiver signal processing
for joint modulation classification and symbol recovery. The proposed approach consists of …

… Our approach to symbol detection implements the Viterbi channel-… an ML-based symbol
detector integrating deep learning into the … , an ML-based symbol decoder based on the Viterbi …

… method is that in the equalization step of the baseline model, the equalization only has
access to 4 symbols, while deep learning method gives out each prediction based on the whole …

… Our design is inspired by deep unfolding, which is a common … ML-based symbol detector
integrating deep learning into the Viterbi … , an ML-based symbol decoder based on the Viterbi …

… in deep learning for the design of MIMO receivers. In particular, we leverage deep neural …
A symbol-wise optimal MIMO receiver decodes each information bit, bk, from the received …

… of coded symbols. In this paper, we propose using deep learning approaches to decode
fixed-… Traditional encoding and decoding of fixed-length CS codes rely on look-up tables (LUTs), …

… idea of using deep neural networks for one-shot decoding of … that (i) structured codes are
easier to learn and (ii) the neural … that neural networks can learn a form of decoding algorithm, …

… the nonlinear mapping of information bits directly to transmit symbols (bypassing modulation)
and yet possess an efficient, high performance decoder. The key technical innovation that …

… learn both the encoder and the decoder via deep learning … We model both the encoder and
the decoder as neural networks… Optimal decoding of linear codes for minimizing symbol error …